Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,063 records · Page 59
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Training data selection for event classification in a highly variable environment

A problem of interest for nuclear nonproliferation is monitoring activities at nuclear facilities, where proliferation events may only take place a few times and often under variable conditions. Machine learning has revolutionized data analytics by enabling the use of measurable signatures to generate predictive models of facility operations. However, traditional methods for training these models require large, reliable data sets with labeled observations, a challenge for nonproliferation. Highly variable conditions further complicate this as events from training data may have occurred in conditions quite different from the event of interest. Our hypothesis is that when events occur in a highly variable environment, careful training data selection for each test event could outperform the standard approach of using all available training data. We developed a method to optimize training data selection for the given test event and applied it to predicting the power level of the High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory. In this study, the reactor startup exhibits variability between occurrences due to natural variability in environmental conditions and operational procedures. Using a combination of analysis techniques, a similitude assessment was performed on data collected from HFIR to isolate clusters that were optimal for training a predictive model. Concepts such as dynamic time warping and Jaccard similarity were used in conjunction with clustering analysis. In order to validate this approach, the model was trained on every combination of unique training events and the predictive performance was compared to the performance using a subset of the training data selected by isolated clusters found through the similitude assessment.

Iyer, A↗
DOE OSTI2014

SU-E-J-125: Classification of CBCT Noises in Terms of Their Contribution to Proton Range Uncertainty

Purpose: This study assesses the potential use of CBCT images in adaptive protontherapy by estimating the contribution of the main sources of noise and calibration errors to the proton range uncertainty. Methods: Measurements intended to highlight each particular source have been achieved by adapting either the testbench configuration, e.g. use of filtration, fan-beam collimation, beam stop arrays, phantoms and detector reset light, or the sequence of correction algorithms including water precorrection. Additional Monte-Carlo simulations have been performed to complement these measurements, especially for the beam hardening and the scatter cases. Simulations of proton beams penetration through the resulting images have then been carried out to quantify the range change due to these effects. The particular case of a brain irradiation is considered mainly because of the multiple effects that the skull bones have on the internal soft tissues. Results: On top of the range error sources is the undercorrection of scatter. Its influence has been analyzed from a comparison of fan-beam and full axial FOV acquisitions. In this case, large range errors of about 12 mm can be reached if the assumption is made that the scatter has only a constant contribution over the projection images. Even the detector lag, which a priori induces a much smaller effect, has been shown to contribute for up to 2 mm to the overall error if its correction only aims at reducing the skin artefact. This last result can partially be understood by the larger interface between tissues and bones inside the skull. Conclusion: This study has set the basis of a more systematical analysis of the effect CBCT noise on range uncertainties based on a combination of measurements, simulations and theoretical results. With our method, even more subtle effects such as the cone-beam artifact or the detector lag can be assessed. SBR and JOR are financed by iMagX, a public-private partnership between the region Wallone of Belgium and IBA under convention #1217662.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2016

TH-AB-209-11: Breast Microcalcification Classification Using Spectral X-Ray Coherent Scatter Computed Tomography

Purpose: To investigate the ability of Coherent Scatter Computed Tomography (CSCT) to distinguish non-invasively between type I calcifications, consisting of calcium oxalate dihydrate (CO) compounds which are more often associated with benign lesions, and type II calcifications containing hydroxyapatite (HA) which are predominantly associated with malignant tumors. Methods: The coherent scatter cross sections of HA and CO were measured using an energy dispersive x-ray diffractometer. The measured cross sections were introduced into MC-GPU Monte Carlo simulation code for studying the applicability of CSCT to discriminate between the two types of microcalcifications within the whole breast. Simulations were performed on a virtual phantom with inserted HA and CO spots of different sizes and placed in regions of interest having different background compositions. We considered a polychromatic x-ray source and an energy resolving photon counting detector. We applied an algorithm that estimates scatter components in projection space in order to obtain material-specific images of the breast. As material components adipose, glandular, HA and CO were used. The relative contrast of HA and CO components were used for type I and type II microcalcification discrimination. Results: The reconstructed CSCT images showed material-specific component-contrast values, with the highest CO or HA component contrast corresponding generally to the actual CO or HA feature, respectively. The discrimination performance varies with the x-ray intensity, calcification size, and background composition. The results were summarized using receiver operating characteristic (ROC) analysis with the area under the curve (AUC) taken as an overall indicator of discrimination performance and showing high AUC values up to unity. Conclusion: The simulation results obtained for a uniform breast imaging phantom indicate that CSCT has potential to be used as a non-invasive method for discrimination between type I and type II microcalcifications.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Exploring the universality of hadronic jet classification

The modeling of jet substructure significantly differs between Parton Shower Monte Carlo (PSMC) programs. Despite this, we observe that machine learning classifiers trained on different PSMCs learn nearly the same function. This means that when these classifiers are applied to the same PSMC for testing, they result in nearly the same performance. This classifier universality indicates that a machine learning model trained on one simulation and tested on another simulation (or data) will likely be optimal. Our observations are based on detailed studies of shallow and deep neural networks applied to simulated Lorentz boosted Higgs jet tagging at the LHC.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2011

Modeling Personalized Email Prioritization: Classification-based and Regression-based Approaches

Email overload, even after spam filtering, presents a serious productivity challenge for busy professionals and executives. One solution is automated prioritization of incoming emails to ensure the most important are read and processed quickly, while others are processed later as/if time permits in declining priority levels. This paper presents a study of machine learning approaches to email prioritization into discrete levels, comparing ordinal regression versus classier cascades. Given the ordinal nature of discrete email priority levels, SVM ordinal regression would be expected to perform well, but surprisingly a cascade of SVM classifiers significantly outperforms ordinal regression for email prioritization. In contrast, SVM regression performs well -- better than classifiers -- on selected UCI data sets. This unexpected performance inversion is analyzed and results are presented, providing core functionality for email prioritization systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A Compound Data Poisoning Technique with Significant Adversarial Effects on Transformer-based Sentiment Classification Tasks

Transformer-based models have demonstrated much success in various natural language processing tasks. However, they are often vulnerable to adversarial attacks, such as data poisoning, which can intentionally fool the model into generating incorrect results. In this article, we present a novel, compound variant of a data poisoning attack on a transformer-based model that maximizes the poisoning effect while minimizing the scope of poisoning. Here we do so by combining the established data poisoning technique (label flipping) with a novel adversarial artifact selection and insertion technique aimed at minimizing detectability and the scope of the poisoning footprint. We find that by using a combination of these two techniques, we achieve a state-of-the-art attack success rate of approximately 90% while poisoning only 0.5% of the original training set, thus minimizing the scope and detectability of the poisoning action. These findings have the potential to advance the development of better data poisoning detection methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Data-Driven Clustering and Classification of Outage Patterns with Insights into their Links to Extreme Events

At a global level extreme events have increased in both scale and impact. These events have the potential to affect the electrical grid infrastructure and cause a wide range of outages, which can lead to a disruption in daily patterns, cost millions of dollars and also the loss of life. Currently, to track these outage events there have been various approaches developed ranging from regional to national level quantifications for what defines an outage. However, this variation in methods can potentially lead to subjective decision-making and a lack of proper management in relation to the event. While previous work has made strides in determining spatio-temporal patterns, minimal attention has been given to the type and number of outages an area may be exposed to. The differences in incurred cost and the overall severity of an event between a transformer box malfunction and a hurricane are drastic, and by finding historical signals, we can allow for more efficient management, potentially saving lives and millions of dollars. Here, we leverage unsupervised machine learning techniques to delineate outage patterns among 22 counties within the United States and find that there are clear, segregated clusters (0.93 silhouette) of data which are related by event behavior and underlying cause. This finding will allow for energy stakeholders, policy makers, and researchers to gain a deeper understanding of the extent and severity of historic events and to better prepare for electrical grid infrastructure planning and management.

Koob, Benjamin [ORNL]↗
DOE OSTI2017

Comparative Analysis and Classification of Cassette Exons and Constitutive Exons

Alternative splicing (AS) is a major engine that drives proteome diversity in mammalian genomes and is a widespread cause of human hereditary diseases. More than 95% of genes in the human genome are alternatively spliced, and the most common type of AS is the cassette exon. Recent discoveries have demonstrated that the cassette exon plays an important role in genetic diseases. To discover the formation mechanism of cassette exon events, we statistically analyze cassette exons and find that cassette exon events are strongly influenced by individual exons that are smaller in size and that have a lower GC content, more codon terminations, and weaker splice sites. We propose an improved random-forest-based hybrid method of distinguishing cassette exons from constitutive exons. Our method achieves a high accuracy in classifying cassette exons and constitutive exons and is verified to outperform previous approaches. It is anticipated that this study will facilitate a better understanding of the underlying mechanisms in cassette exons.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices

The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series generated by diagnostic instruments observing fusion plasmas. Here we apply this neural network architecture to the popular problem of disruption prediction in fusion tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. ECEi measures a fundamental plasma quantity (electron temperature) with high temporal resolution over the entire plasma discharge, making it sensitive to a number of potential pre-disruptions markers with different temporal and spatial scales. Promising, initial disruption prediction results are obtained training a deep CNN with large receptive field ({$\sim$}30k), achieving an $F_1$-score of {$\sim$}91\% on individual time-slices using only the ECEi data.

convolutional neural networks↗
DOE OSTI2018

Automatic Residential/Commercial Classification of Parcels with Solar Panel Detections

A computational method to automatically detect solar panels on rooftops to aid policy and financial assessment of solar distributed generation. The code automatically classifies parcels containing solar panels in the U.S. as residential or commercial. The code allows the user to specify an input dataset containing parcels and detected solar panels, and then uses information about the parcels and solar panels to automatically classify the rooftops as residential or commercial using machine learning techniques. The zip file containing the code includes sample input and output datasets for the Boston and DC areas.

Morton, AprilM↗
DOE OSTI2018

Multi-Task Convolutional Neural Networks for Natural Text Classification

Information extraction and coding of free-text pathology reports is an important activity for cancer registries to support national cancer surveillance. Cancer registrars must process high volumes of pathology reports on an annual basis. We investigated an automated approach using a convolutional neural networks (CNNs) for extracting the primary site, laterality, histology, behavior, and histological grade from unstructured cancer pathology text reports. Our multi-task learning (MTL) with hard parameter sharing approach is used to train a multi-task MT-CNN model for all the tasks. The performance of our proposed approach was compared against a state of-the-art CNN and the commonly used SVM classifier. We observed that the proposed model consistently outperformed the baseline models, especially for the less prevalent classes. Also, the results demonstrate the potential of the proposed method for handling class imbalance within each task.

Yoon, HongJun↗
DOE OSTI2026

Hyperdimensional computing for image classification (HDC) v1.0

This is an implementation of the hyperdimensional computing technique to classify images. It consists of a python script that trains the system for a set of images from a set of images (dataset) specified by the user. This training produces hardware configuration parameters and description vectors that are then loaded into the hardware description part of the project. The hardware description consists of hardware described in Verilog (a well known language for this purpose) that is synthesizable and can be implemented in a real chip. This hardware received the training information generated by python, and then is able to accept images to produce answers for each image on which category (class) from the pre-=trained ones the image belongs to. The hardware and python training scripts are configurable and documented. The advantage of hyperdimensional computing is its robustness to errors and the easy capability for online learning (refining the training during inference slowly over time), which this implementation supports.

Michelogiannakis, Georgios [Lawrence Berkeley Nati↗
DOE OSTI2025

GRinding Automated Classification Engine

This work is an ML-driven framework for automated surface analysis of microscopy images. We create a training dataset by imaging stainless steel samples to benchmark four developed deep neural network architectures. These models, based on a YOLOv8n-cls backend, integrate image features and process metadata using various fusion methods to distinguish between acceptable and unacceptable surface finishes. This code is associated with publication "Classifying Alloy Surface Preparation Quality with Metadata-Infused Machine Learning for Rapid Alloy Discovery" for project APEX LDRD-ER (25-ERD-039)

Gongora, AldairE [Lawrence Livermore National Labo↗